Noometry

Anthropic, proprietary

Claude Opus 5.5

Claude Opus 5.5 by Anthropic ranks 3rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 68.6. Its strongest category is multimodal, where it ranks 1st. API pricing starts at $4 per million input tokens and $20 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#3 of 354
Index score
68.6
Evidence
Confirmed 44 results
Provider
Anthropic
Released
September 22, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
128K
Input price
$4 / M
Output price
$20 / M
Blended price
$8 / M
Output speed
Not measured
Value
#190 of 219
Knowledge cutoff
June 2026
Input
text, image, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 71.9
  2. Agentic & Tool Use 45.3
  3. Reasoning 80.2
  4. Math 91.8
  5. Knowledge 66.4
  6. Multimodal 57.8
  7. Multilingual 59.1
  8. Instruction Following 80.0
  9. Long Context 47.1
  10. Writing & Preference 78.2
CategoryScoreRankResults
Coding71.9#37
Agentic & Tool Use45.3#152
Reasoning80.2#39
Math91.8#35
Knowledge66.4#103
Multimodal57.8#13
Multilingual59.1#21
Instruction Following80.0#31
Long Context47.1#191
Writing & Preference78.2#34

Strengths and weaknesses

Categories where Claude Opus 5.5 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Multilingual59.1+11.7#2 of 297, top 1%
Multimodal57.8+19.2#1 of 128, top 1%
Reasoning80.2+56.6#3 of 350, top 1%

Weakest categories

CategoryScorevs medianRank
Agentic & Tool Use45.3+14.9#15 of 154, top 10%
Long Context47.1+6.1#19 of 296, top 7%
Knowledge66.4+29.1#10 of 314, top 4%

Closest competitors

The models ranked just above and below Claude Opus 5.5. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
GPT-6 Astra#170.8$20—Compare
Claude Fable 5.1#269.0$20—Compare
Claude Opus 5#467.8$10—Compare
Claude Fable 5#566.8$2025Compare
GPT-6.1 Sol#665.6$4—Compare
GPT-5.6 Sol#765.0$810Compare
GPT-5.5 Pro#864.3$67.50—Compare
GPT-5.5#963.4$11.2525Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
FrontierCode54.6%Best of 37mediumEpoch AI
FrontierCode54.4%maxModel card (self-reported)2026-09-22
CursorBench56%highEpoch AI
CursorBench43.7%lowEpoch AI
CursorBench57.8%Best of 14maxEpoch AI
CursorBench52.5%mediumEpoch AI
CursorBench56%xhighEpoch AI
LMArena WebDev1813Best of 113LMArena2026-10-08
FrontierSWE62.3%#2 of 18, top 12%maxEpoch AI
SciCode60.4%highEpoch AI
SciCode58.6%lowEpoch AI
SciCode66.9%Best of 121maxEpoch AI
SciCode59.3%mediumEpoch AI
SciCode65%xhighEpoch AI
LMArena Coding1547#2 of 294, top 1%highLMArena2026-10-08
MirrorCode77.4%Best of 9maxEpoch AI2026-09-22
ALE-Bench2,147#5 of 105, top 5%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents73.5%#3 of 49, top 7%maxEpoch AI
APEX-Agents52.5%mediumEpoch AI
GDP.pdf30.6%#4 of 36, top 12%maxEpoch AI
Vending-Bench 29,235#8 of 60, top 14%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-293.3%#3 of 83, top 4%highEpoch AI
ARC-AGI-270.1%lowEpoch AI
ARC-AGI-291.7%maxEpoch AI
ARC-AGI-287.5%mediumEpoch AI
ARC-AGI-292.5%xhighEpoch AI
NYT Connections (extended)88.5%#23 of 91, top 26%high reasoningLech Mazur benchmarks
ARC-AGI-198.5%#2 of 83, top 3%highEpoch AI
ARC-AGI-188.5%lowEpoch AI
ARC-AGI-197.5%maxEpoch AI
ARC-AGI-197.5%mediumEpoch AI
ARC-AGI-197.5%xhighEpoch AI
CritPt30.9%highEpoch AI
CritPt17.7%lowEpoch AI
CritPt31.7%#2 of 134, top 2%maxEpoch AI
CritPt27.7%mediumEpoch AI
CritPt31.7%xhighEpoch AI
EBR-Bench71.4%#2 of 24, top 9%maxEpoch AI2026-09-22
LMArena Hard Prompts1535#2 of 297, top 1%highLMArena2026-10-08
Mystery Game Puzzles71%#3 of 74, top 5%maxEpoch AI2026-09-29
DTBench98.9%Best of 151maxEpoch AI
LMCA68.2%Best of 125maxEpoch AI
Epoch Capabilities Index167.33Best of 213Epoch AI2026-09-22

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)91.2%#3 of 81, top 4%maxEpoch AI2026-09-22
FrontierMath Tier 495%#3 of 63, top 5%maxEpoch AI2026-09-22
OTIS Mock AIME 2024-2025100%#3 of 173, top 2%maxEpoch AI2026-09-22
ProofBench100%#2 of 77, top 3%maxEpoch AI
LMArena Math1506#9 of 285, top 4%highLMArena2026-10-08
FrontierMath Erdős2.9%#2 of 7, top 29%maxEpoch AI2026-09-24

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond90.6%#33 of 186, top 18%maxEpoch AI2026-09-22
SimpleQA Verified72.2%#4 of 77, top 6%maxEpoch AI2026-09-22
LMArena Expert1547#3 of 273, top 2%highLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1321#2 of 122, top 2%highLMArena2026-10-09
Blueprint-Bench 251.2%#2 of 31, top 7%Epoch AI
Furniture Assembly83.3%Best of 31maxEpoch AI2026-09-22

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1507#2 of 297, top 1%highLMArena2026-10-08
LMArena Chinese1588#2 of 285, top 1%highLMArena2026-10-08
LMArena French1514#4 of 223, top 2%highLMArena2026-10-08
LMArena Russian1520#3 of 283, top 2%highLMArena2026-10-08
LMArena Spanish1507#4 of 226, top 2%highLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1537#2 of 298, top 1%highLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1532#2 of 291, top 1%highLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1515#2 of 297, top 1%highLMArena2026-10-08
LMArena Creative Writing1533Best of 295highLMArena2026-10-08
EQ-Bench Creative Writing2050#7 of 115, top 7%EQ-Bench
LMArena Multi-Turn1499#6 of 295, top 3%highLMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
anthropic$4$20$0.202026-10-10
azure$4$20$0.202026-10-10
bedrock$4$20$0.202026-10-10
openrouter$4$20$0.202026-10-10
vertex$4$20$0.202026-10-10

All Anthropic API prices → Estimate your cost →

Compare Claude Opus 5.5

Other Anthropic models

Frequently asked questions

How good is Claude Opus 5.5?

Claude Opus 5.5 by Anthropic ranks 3rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 68.6. Its strongest category is multimodal, where it ranks 1st. API pricing starts at $4 per million input tokens and $20 per million output tokens, with a 1M-token context window.

How much does Claude Opus 5.5 cost?

Claude Opus 5.5 costs $4 per million input tokens and $20 per million output tokens on Anthropic's own API, with cached input at $0.20.

What is Claude Opus 5.5's context window?

Claude Opus 5.5 accepts up to 1M tokens of input and can write up to 128K tokens in one response.

Is Claude Opus 5.5 open source?

No. Claude Opus 5.5 is proprietary and available only through Anthropic's API and partner platforms.

What are Claude Opus 5.5's strengths and weaknesses?

Relative to other ranked models, Claude Opus 5.5 places best in multilingual, multimodal, reasoning and lowest in agentic & tool use, long context, knowledge.

What is Claude Opus 5.5 best at?

Its best category is multimodal, where it ranks 1st on Noometry.